estimate_context_size

THE RISK

Low Risk

Why estimate_context_size needs a policy

This tool retrieves and analyzes metadata about conversations to report token/context usage statistics. It performs no side effects, creates no data, executes no code, and cannot modify or delete anything. It is a pure observation/monitoring function, fitting squarely within the Read category. The low severity reflects that misuse would only expose informational metrics, not cause operational harm.

From the tool's definition Tool description states it 'estimate' and 'shows breakdown' of context/token usage—purely informational operations with no modification, deletion, or execution of code. The verb 'estimate' and 'shows' indicate read-only analysis.

Documented attack patterns abuse exactly the kind of access estimate_context_size gives an agent:

POLICY

How to control estimate_context_size

PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Code Toolkit, and nothing reaches the server without passing your rules. This is the rule we recommend for estimate_context_size:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "estimate_context_size": {}
  }
}

estimate_context_size is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Claude Code Toolkit — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Claude Code Toolkit tools

Destructive cleanup_backups Delete old backup files to free up disk space. Destructive wipe_traces Securely wipe ALL Claude Code traces. Overwrites files with zeros before deletion. Require Destructive clean_claude_directory Analyze and clean the .claude directory. Removes debug logs, empty todos, old snapshots, a Destructive clean_traces Selectively clean Claude Code traces by category, age, or project. Destructive enforce_retention Apply data retention policy by deleting sessions older than specified days. Execute run_doctor Full integrity check: detects corrupted JSONL lines, truncated thinking blocks, oversized Execute run_maintenance Run maintenance checks on Claude Code installation. Identifies issues, old backups, and ar Execute start_dashboard Start the web dashboard on a local port. Returns the URL to open in a browser.

All 40 Claude Code Toolkit tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about estimate_context_size

What does the estimate_context_size tool do? +

Estimate the context/token usage of a Claude Code conversation. Shows breakdown by message type, images, documents, and tool usage. It is categorised as a Read tool in the Claude Code Toolkit MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on estimate_context_size? +

Register the Claude Code Toolkit MCP server in PolicyLayer and add a rule for estimate_context_size: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Code Toolkit. Nothing to install.

What risk level is estimate_context_size? +

estimate_context_size is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit estimate_context_size? +

Yes. Add a rate_limit block to the estimate_context_size rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block estimate_context_size completely? +

Set action: deny in the PolicyLayer policy for estimate_context_size. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides estimate_context_size? +

estimate_context_size is provided by the Claude Code Toolkit MCP server (asifkibria/claude-code-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Claude Code Toolkit tool call.

Start from Claude Code Toolkit, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →